NSF_TCPP - summary
 Share
The version of the browser you are using is no longer supported. Please upgrade to a supported browser.Dismiss

View only
 
ABCDEFGHIJ
1
2
NSF/IEEE-TCPP Parallel and Distributed Computing Curriculular Recommendations
3
4
B
5
L
6
TopicsOWhereItems
7
OCovered
8
M
9
#
10
11
Architecture Topics
12
13
Classes
14
TaxonomyCSystems
15
Data vs. control parallelismK,CSystemsSuperscalar (ILP); SIMD/Vector; Pipelines; Streams (e.g., GPU); MIMD; Simultaneous Multi-Threading; Multicore; Heterogeneous (e.g., Cell, on-chip GPU)
16
Shared vs. distributed memoryK,CSystemsSMP (Buses); Message passing (Latency, Bandwidth)
17
Memory HierarchyCSystemsCache organization
18
Floating point representationKCS1, CS2, SystemsRange; Precision; Error propagation; IEEE 754 standard
19
Performance metricsK,CSystemsCycles per instruction (CPI); Benchmarks (incl. Spec mark); Peak performance (incl. MIPS/FLOPS); Sustained performance
20
21
Programming Topics
22
23
Parallel Programming paradigms and Notations
24
By the target machine modelK,C,ACS2, DS/A, Systems, LangSIMD (incl. Processor vector extensions); Shared memory (incl. Language extensions, Compiler directives/ pragmas, Libraries); Distributed memory (incl. Client Server); Hybrid
25
By the control statementC,ACS2, DS/A, LangTask/thread spawning; SPMD (incl. SPMD notations); Data parallel (incl. Parallel loops for shared memory)
26
Semantics and correctness issuesK,C,ACS2, DS/A, Systems, LangTasks and threads; Synchronization (incl. Critical regions, Producer-consumer, Monitors); Concurrency defects (incl. Deadlocks, Data Races); Tools to detect concurrency defects
27
Performance issues
28
ComputationCCS2, DS/A, SystemsComputation decomposition strategies (Owner computes rule, Decomposition into atomic tasks); Load balancing; Scheduling and mapping (Static, Dynamic)
29
DataK,CCS2, DS/A, Systems, LangData distribution; Data layout; Data locality; False sharing; Performance monitoring tools; Performance metrics (Speedup, Efficiency, Amdahl’s law, Gustafson’s Law)
30
31
Algorithm Topics
32
33
Parallel and Distributed Models and ComplexityK,C,ACS1, CS, DS/A, SWECosts of computation (Asymptotics, Time, Space/Memory); Cost reduction (Speedup); Scalability in algorithms and architectures; Model-based notions (Notions from complexity-theory [PRAM, BSP/CILK], Notions from scheduling [ Dependencies, Task graphs, Work, (Make)span])
34
Algorithmic ParadigmsK,CCS2, DS/A, Systems, Alg2Divide & conquer (parallel aspects); Recursion (parallel aspects); Reduction (map-reduce); Dependencies; Series-parallel composition
35
Algorithmic problemsK,C,ACS, DS/A, ParAlgCommunication (Broadcast, Multicast, Scatter/gather); Asynchrony; Synchronization; Sorting; Selection; Graph algorithms (Search); Specialized computations; Termination detection; Leader election/symmetry breaking
36
37
Cross Cutting and Advanced Topics
38
39
High level themesKCS1, CS2Why and what is parallel/distributed computing?
40
Cross-Cutting topicsK,CCS2, DS/A, SystemsLocality; Concurrency; Non-determinism; Power Consumption; Fault tolerance
41
Current/Advanced TopicsKCS1, CS2, DS/A, SystemsCluster Computing; Cloud/grid Computing; Peer to Peer Computing; Consistency in Distributed Transactions; Web search; Security in Distributed Systems
42
Loading...